WO2023141985A1

WO2023141985A1 - Communication method and apparatus

Info

Publication number: WO2023141985A1
Application number: PCT/CN2022/074781
Authority: WO
Inventors: 封召; 辛阳; 王远; 韦庆
Original assignee: 华为技术有限公司
Priority date: 2022-01-28
Filing date: 2022-01-28
Publication date: 2023-08-03

Abstract

The present application provides a communication method and apparatus. The method comprises: a service providing network element obtains feature information of a data analysis network element, the feature information comprising a model operation platform type and/or a model interoperation standard supported by the data analysis network element; the service providing network element receives a request message from a service request network element, the request message being used for requesting to discover a target data analysis network element, and the request message comprising a model operation platform type and/or a model interoperation standard required by the service request network element; the service providing network element determines the target data analysis network element according to the feature information and the request message; the service providing network element sends address information and/or identification information of the target data analysis network element to the service request network element. The target data analysis network element and the service request network element may belong to different manufacturers, thereby realizing cross-manufacturer distribution of an AI model, breaking through the limitation that an AI model can only be shared by the same manufacturer, and improving the flexibility of AI model distribution.

Description

Communication method and device

technical field

The present application relates to the technical field of communication, and more specifically, to a communication method and device.

Background technique

Network data analysis function (network data analytics function, NWDAF) network elements can be divided into NWDAF that supports model reasoning, NWDAF that supports model training, and NWDAF that supports model training and reasoning. Among them, the NWDAF that supports inference can request an artificial intelligence (AI) model (also called a machine learning (machine learning, ML) model) from the NWDAF that supports model training, or from the NWDAF that supports model training and inference, to perform data processing. reasoning.

Currently, in order to obtain the AI model, the NWDAF that supports inference is configured with the addresses of one or more NWDAFs that support model training, and the NWDAF that supports inference and the NWDAF that supports model training belong to the same manufacturer. When there is an AI model requirement, the NWDAF that supports reasoning selects the appropriate NWDAF that supports model training.

However, due to cost and other considerations, a certain manufacturer only deploys some types of NWDAF. For example, it only deploys NWDAF that supports inference, but does not deploy NWDAF that supports model training. As a result, the manufacturer's NWDAF cannot obtain the corresponding model for data analysis.

Contents of the invention

This application provides a communication method and device, which breaks the limitation that models can only be shared with manufacturers.

In a first aspect, a communication method is provided, including:

The service providing network element obtains the feature information of the data analysis network element, and the feature information includes at least one of the type of model running platform supported by the data analysis network element and the model interoperability standard supported by the data analysis network element; the service providing network element receives from the service request The request message of the network element, the request message is used to request the discovery of the target data analysis network element, the request message includes the type of model running platform required by the service requesting network element and/or the model interoperability standard required by the service requesting network element; the service providing network element according to The characteristic information and the request message determine the target data analysis network element, and the data analysis network element includes the target data analysis network element; the service providing network element sends the address information and/or identification information of the target data analysis network element to the service requesting network element.

It should be understood that there may be at least one data analysis network element, and the target data analysis network element is used to provide the AI model or the address information of the AI model.

According to the method of the present application, the service providing network element determines the target data analysis network element according to the feature information of the data analysis network element and the request message of the service requesting network element. The target data analysis network element and the service request network element may belong to different vendors, so that the AI model can be distributed across vendors, breaking the limitation that the AI model can only be shared with the vendor, and improving the flexibility of AI model distribution.

In combination with the first aspect, in some implementations of the first aspect, the type of model running platform supported by the target data analysis network element includes the type of model running platform required by the service request network element, and the model interoperability standard supported by the target data analysis network element The model interoperability standard required by the service request network element is not included; or, the model operation platform type supported by the target data analysis network element does not include the model operation platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element Including the model interoperability standard required by the service request network element; or, the type of model running platform supported by the target data analysis network element includes the model running platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element includes service Request model interoperability standards required by network elements.

With reference to the first aspect, in some implementation manners of the first aspect, the service providing network element determines the target data analysis network element according to the feature information and the request message, including:

The service provider network element determines the target data analysis network element according to the model running platform type and the priority of the model interoperability standard.

With reference to the first aspect, in some implementation manners of the first aspect, the priority of the model running platform type is higher than that of the model interoperability standard.

In combination with the first aspect, in some implementations of the first aspect, the method further includes:

The service providing network element sends the model running platform type supported by the target data analysis network element and/or the model interoperability standard supported by the target data analysis network element to the service requesting network element.

In combination with the first aspect, in some implementations of the first aspect, the feature information also includes the type of the data analysis network element, the type of analysis supported by the data analysis network element, the manufacturer identification of the data analysis network element, and the service of the data analysis network element Region ID.

In combination with the first aspect, in some implementations of the first aspect, the service providing network element is a network storage function network element; the service requesting network element is a network data analysis function network element supporting reasoning; the target data analysis network element is a supporting model The network data analysis function network element for training, or the network data analysis function network element supporting reasoning and model training.

In a second aspect, a communication method is provided, including:

The service requesting network element sends a request message to the service providing network element. The request message is used to request the discovery of the target data analysis network element. The request message includes the type of model running platform required by the service requesting network element and/or the model interoperability required by the service requesting network element Standard; the service requesting network element receives the address information and/or identification information of the target data analysis network element from the service providing network element; the service requesting network element sends a model request message to the target data analysis network element according to the address information and/or identification information, The model request message includes the target analysis type, and the model request message is used to request the model corresponding to the target analysis type; the service request network element receives the model corresponding to the target analysis type from the target data analysis network element, or the address of the model corresponding to the target analysis type.

In combination with the second aspect, in some implementations of the second aspect, the type of model running platform supported by the target data analysis network element includes the type of model running platform required by the service request network element, and the model interoperability standard supported by the target data analysis network element The model interoperability standard required by the service request network element is not included; or, the model operation platform type supported by the target data analysis network element does not include the model operation platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element Including the model interoperability standard required by the service request network element; or, the type of model running platform supported by the target data analysis network element includes the model running platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element includes service Request model interoperability standards required by network elements.

With reference to the second aspect, in some implementation manners of the second aspect, the method further includes:

The service request network element receives the target data analysis network element from the service providing network element Supported model running platform type and/or the model interoperability standard supported by the target data analysis network element; the model running platform type supported by the target data analysis network element does not include The type of model running platform required by the service requesting network element, the model interoperability standard supported by the target data analysis network element includes the model interoperability standard required by the service requesting network element, and the model request message includes the model interoperability standard required by the service requesting network element.

In combination with the second aspect, in some implementations of the second aspect, the service providing network element is a network storage function network element; the service requesting network element is a network data analysis function network element supporting reasoning; the target data analysis network element is a support model The network data analysis function network element for training, or the network data analysis function network element supporting reasoning and model training.

In a third aspect, a communication method is provided, including:

The service providing network element obtains the characteristic information of the first data analysis network element, and the characteristic information includes the analysis type supported by the first data analysis network element; the service providing network element receives a request message from the service requesting network element, and the request message is used to request to discover the first data analysis network element. Two data analysis network elements, the request message includes the target analysis type, the analysis type supported by the second data analysis network element includes the target analysis type; the first data analysis network element includes the second data analysis network element; the service providing network element according to the characteristic information and The request message determines the second data analysis network element; the service providing network element sends at least one of the model running platform type supported by the second data analysis network element and the model interoperability standard supported by the second data analysis network element to the service requesting network element, And the second data analyzes the address information and/or identification information of the network element.

It should be understood that the first data analysis network element includes at least one data analysis network element, and the second data analysis network element is a candidate data analysis network element hereinafter.

With reference to the third aspect, in some implementation manners of the third aspect, the feature information further includes the model running platform type supported by the first data analysis network element and/or the model interoperability standard supported by the first data analysis network element.

With reference to the third aspect, in some implementations of the third aspect, the feature information also includes the type of the first data analysis network element, the manufacturer identifier of the first data analysis network element, and the service area identifier of the first data analysis network element at least one of the .

In combination with the third aspect, in some implementations of the third aspect, the service providing network element is a network storage function network element; the service requesting network element is a network data analysis function network element supporting reasoning; the second data analysis network element includes support A network element with a network data analysis function for model training, and/or a network element with a network data analysis function that supports reasoning and model training.

In a fourth aspect, a communication method is provided, including:

The service requesting network element sends a request message to the service providing network element. The request message is used to request the discovery of candidate data analysis network elements. The request message includes the target analysis type, and the analysis types supported by the candidate data analysis network element include the target analysis type; the service request network element Receive the feature information of the candidate data analysis network element from the service providing network element, the feature information includes at least one of the model running platform type supported by the candidate data analysis network element and the model interoperability standard supported by the candidate data analysis network element; the service request network The element determines the target data analysis network element according to the feature information; the candidate data analysis network element includes the target data analysis network element; the service request network element sends a model request message to the target data analysis network element, and the model request message is used to request the corresponding target analysis type model; the service request network element receives the model corresponding to the target analysis type or the address of the model corresponding to the target analysis type from the target data analysis network element.

It should be understood that the target data analysis network element is used to provide the AI model or the address information of the AI model.

According to the method of the present application, the service requesting network element can determine the target data analysis network element according to the characteristic information of the candidate data analysis network element. The target data analysis network element and the service request network element may belong to different vendors, so that the AI model can be distributed across vendors, breaking the limitation that the AI model can only be shared with the vendor, and improving the flexibility of AI model distribution.

In combination with the fourth aspect, in some implementations of the fourth aspect, the type of model running platform supported by the target data analysis network element includes the type of model running platform required by the service request network element, and the model interoperability standard supported by the target data analysis network element The model interoperability standard required by the service request network element is not included; or, the model operation platform type supported by the target data analysis network element does not include the model operation platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element Including the model interoperability standard required by the service request network element; or, the type of model running platform supported by the target data analysis network element includes the model running platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element includes service Request model interoperability standards required by network elements.

With reference to the fourth aspect, in some implementation manners of the fourth aspect, the service requesting network element determines the target data analysis network element according to characteristic information, including:

The service request network element determines the target data analysis network element according to the model running platform type and the priority of the model interoperability standard.

With reference to the fourth aspect, in some implementation manners of the fourth aspect, the priority of the model running platform type is higher than that of the model interoperability standard.

In combination with the fourth aspect, in some implementations of the fourth aspect, the model running platform type supported by the target data analysis network element does not include the model running platform type required by the service request network element, and the model interoperability supported by the target data analysis network element The standard includes the model interoperability standard required by the service requesting network element, and the model request message includes the model interoperability standard required by the service requesting network element.

In combination with the fourth aspect, in some implementations of the fourth aspect, the service providing network element is a network storage function network element; the service requesting network element is a network data analysis function network element supporting reasoning; the candidate data analysis network element includes a supporting model The trained network data analysis function network element, and/or, the network data analysis function network element that supports reasoning and model training; the target data analysis network element is the network data analysis function network element that supports model training, or, supports reasoning and model training Trained network data analysis function network elements.

In the fifth aspect, a communication method is provided, including:

The data analysis network element generates characteristic information of the data analysis network element, and the characteristic information includes at least one of the type of model running platform supported by the data analysis network element and the model interoperability standard supported by the data analysis network element; Element sends characteristic information.

With reference to the fifth aspect, in some implementation manners of the fifth aspect, the feature information further includes one or more of the following:

The type of the data analysis network element, the analysis type supported by the data analysis network element, the manufacturer identification of the data analysis network element, and the service area identification of the data analysis network element.

According to a sixth aspect, a communication device is provided, including: a transceiver unit and a processing unit connected to the transceiver unit.

The transceiver unit is used to obtain the characteristic information of the data analysis network element, and the characteristic information includes at least one of the model running platform type supported by the data analysis network element and the model interoperability standard supported by the data analysis network element; The request message of the service request network element, the request message is used to request the discovery of the target data analysis network element, the request message includes the type of model running platform required by the service request network element and/or the model interoperability standard required by the service request network element; the processing unit, It is used to determine the target data analysis network element according to the characteristic information and the request message; the sending and receiving unit is used to send the address information and/or identification information of the target data analysis network element to the service requesting network element.

In combination with the sixth aspect, in some implementations of the sixth aspect, the type of model running platform supported by the target data analysis network element includes the type of model running platform required by the service request network element, and the model interoperability standard supported by the target data analysis network element The model interoperability standard required by the service request network element is not included; or, the model operation platform type supported by the target data analysis network element does not include the model operation platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element Including the model interoperability standard required by the service request network element; or, the type of model running platform supported by the target data analysis network element includes the model running platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element includes service Request model interoperability standards required by network elements.

With reference to the sixth aspect, in some implementation manners of the sixth aspect, the processing unit is configured to determine the target data analysis network element according to the model running platform type and the priority of the model interoperability standard.

With reference to the sixth aspect, in some implementation manners of the sixth aspect, the priority of the model running platform type is higher than that of the model interoperability standard.

With reference to the sixth aspect, in some implementation manners of the sixth aspect, the transceiver unit is configured to send the model running platform type supported by the target data analysis network element and/or the model interaction platform supported by the target data analysis network element to the service requesting network element. operating standards.

In combination with the sixth aspect, in some implementations of the sixth aspect, the feature information also includes the type of the data analysis network element, the type of analysis supported by the data analysis network element, the manufacturer identification of the data analysis network element, and the service of the data analysis network element At least one of the zone IDs.

According to a seventh aspect, a communication device is provided, including: a transceiver unit and a processing unit connected to the transceiver unit.

The transceiver unit is configured to send a request message to the service providing network element, the request message is used to request to discover the target data analysis network element, and the request message includes the type of model running platform required by the service requesting network element and/or the model interaction required by the service requesting network element Operating standard; the transceiver unit is used to receive the address information and/or identification information of the target data analysis network element from the service providing network element; the transceiver unit is used to send the model to the target data analysis network element according to the address information and/or identification information The request message, the model request message includes the target analysis type, the model request message is used to request the model corresponding to the target analysis type; the transceiver unit is used to receive the model corresponding to the target analysis type from the target data analysis network element, or the target analysis type corresponding to the model The address of the model.

In combination with the seventh aspect, in some implementations of the seventh aspect, the type of model running platform supported by the target data analysis network element includes the type of model running platform required by the service request network element, and the model interoperability standard supported by the target data analysis network element The model interoperability standard required by the service request network element is not included; or, the model operation platform type supported by the target data analysis network element does not include the model operation platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element Including the model interoperability standard required by the service request network element; or, the type of model running platform supported by the target data analysis network element includes the model running platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element includes service Request model interoperability standards required by network elements.

With reference to the seventh aspect, in some implementations of the seventh aspect, the transceiver unit is configured to receive the model running platform type supported by the target data analysis network element from the service providing network element and/or the model supported by the target data analysis network element Interoperability standards; the model running platform type supported by the target data analysis network element does not include the model running platform type required by the service request network element, the model interoperability standard supported by the target data analysis network element includes the model interoperability standard required by the service request network element , the model request message includes the model interoperability standard required by the service requesting network element.

According to an eighth aspect, a communication device is provided, including: a transceiver unit and a processing unit connected to the transceiver unit.

The transceiver unit is used to obtain the characteristic information of the first data analysis network element, and the characteristic information includes the analysis type supported by the first data analysis network element; the transceiver unit is used to receive the request message from the service request network element, and the request message is used to request The second data analysis network element is found, the request message includes the target analysis type, and the analysis type supported by the second data analysis network element includes the target analysis type; the first data analysis network element includes the second data analysis network element; the processing unit is configured to The characteristic information and the request message determine the second data analysis network element; the sending and receiving unit is used to send the model running platform type supported by the second data analysis network element and the model interoperability standard supported by the second data analysis network element to the service requesting network element at least one, and the address information and/or identification information of the second data analysis network element.

With reference to the eighth aspect, in some implementations of the eighth aspect, the feature information further includes the type of model running platform supported by the first data analysis network element and/or the model interoperability standard supported by the first data analysis network element

With reference to the eighth aspect, in some implementations of the eighth aspect, the feature information also includes the type of the first data analysis network element, the manufacturer identifier of the first data analysis network element, and the service area identifier of the first data analysis network element at least one of the .

According to a ninth aspect, a communication device is provided, including: a transceiver unit and a processing unit connected to the transceiver unit.

The transceiver unit is used to send a request message to the service providing network element, the request message is used to request the discovery of a candidate data analysis network element, the request message includes the target analysis type, and the analysis types supported by the candidate data analysis network element include the target analysis type; the transceiver unit, It is used to receive the feature information of the candidate data analysis network element from the service providing network element, the feature information includes at least one of the model running platform type supported by the candidate data analysis network element and the model interoperability standard supported by the candidate data analysis network element; processing The unit is used to determine the target data analysis network element according to the feature information; the candidate data analysis network element includes the target data analysis network element; the transceiver unit is used to send a model request message to the target data analysis network element, and the model request message is used to request target analysis A model corresponding to the type; a transceiver unit configured to receive the model corresponding to the target analysis type or the address of the model corresponding to the target analysis type from the target data analysis network element.

In conjunction with the ninth aspect, in some implementations of the ninth aspect, the type of model running platform supported by the target data analysis network element includes the type of model running platform required by the service request network element, and the model interoperability standard supported by the target data analysis network element The model interoperability standard required by the service request network element is not included; or, the model operation platform type supported by the target data analysis network element does not include the model operation platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element Including the model interoperability standard required by the service request network element; or, the type of model running platform supported by the target data analysis network element includes the model running platform type required by the service request network element, and the model interoperability standard supported by the target data analysis network element includes service Request model interoperability standards required by network elements.

With reference to the ninth aspect, in some implementation manners of the ninth aspect, the processing unit is configured to determine the target data analysis network element according to the type of the model running platform and the priority of the model interoperability standard.

With reference to the ninth aspect, in some implementation manners of the ninth aspect, the priority of the model running platform type is higher than that of the model interoperability standard.

In conjunction with the ninth aspect, in some implementations of the ninth aspect, the type of model running platform supported by the target data analysis network element does not include the type of model running platform required by the service requesting network element, and the model interoperability supported by the target data analysis network element The standard includes the model interoperability standard required by the service requesting network element, and the model request message includes the model interoperability standard required by the service requesting network element.

According to a tenth aspect, a communication device is provided, including: a transceiver unit and a processing unit connected to the transceiver unit.

The processing unit is used to generate the characteristic information of the data analysis network element, and the characteristic information includes at least one of the type of model running platform supported by the data analysis network element and the model interoperability standard supported by the data analysis network element; Provides network element sending feature information.

With reference to the tenth aspect, in some implementation manners of the tenth aspect, the feature information further includes one or more of the following:

In an eleventh aspect, a communication device is provided, including a communication interface and a processor. When the communication device is running, the processor executes the computer program or instruction stored in the memory, so that the communication device executes the method in any possible implementation manner of the first aspect to the fifth aspect. The memory may be located in the processor, or implemented by a chip independent of the processor, which is not specifically limited in the present application.

In a twelfth aspect, a computer-readable storage medium is provided, including a computer program. When the computer program runs on a computer, the computer executes the method in any possible implementation manner of the first aspect to the fifth aspect.

A thirteenth aspect provides a chip or a chip system, the chip or the chip system includes a processing circuit, and the processing circuit is configured to execute the method in any possible implementation manner of the first aspect to the fifth aspect.

In a fourteenth aspect, a computer program product is provided, and the computer program product includes: a computer program (also referred to as code, or instruction), which, when the computer program is executed, causes the computer to execute any of the first to fifth aspects. A method in one possible implementation.

In a fifteenth aspect, a communication device is provided, including: a memory for storing computer instructions; a processor for executing the computer instructions, so that the communication device performs any one of the first aspect to the fifth aspect method in one possible implementation.

In a sixteenth aspect, a communication system is provided, including a service providing network element and a service requesting network element.

The service network element is configured to execute the method in any possible implementation manner in the first aspect, and the service requesting network element is configured to execute the method in any possible implementation manner in the second aspect; or,

The service network element is configured to execute the method in any possible implementation manner in the third aspect, and the service requesting network element is configured to execute the method in any possible implementation manner in the fourth aspect.

Description of drawings

Fig. 1 shows the system architecture applicable to the embodiment of the present application.

Fig. 2 is a schematic interaction diagram of an example of the method proposed in this application.

Fig. 3 is a schematic interaction diagram of an example of the method proposed in this application.

Fig. 4 is a schematic block diagram of a communication device provided in this application.

Fig. 5 is a schematic block diagram of a communication device provided in this application.

Detailed ways

The technical solutions of the embodiments of the present application can be applied to various 3rd generation partnership project (the 3rd generation partnership project, 3GPP) communication systems, for example: long term evolution (long term evolution, LTE) system, for example, LTE frequency division duplex (frequency division duplex, FDD) system, LTE time division duplex (time division duplex, TDD), fifth generation (5th Generation, 5G) communication system, also known as new wireless (new radio, NR) communication system, future evolution communication system , for example: the sixth generation (6th Generation, 6G) communication system, etc.

FIG. 1 is a schematic diagram of a communication network architecture. The network architecture may specifically include the following network elements:

1. User equipment (UE): can include various handheld devices with wireless communication functions, vehicle-mounted devices, wearable devices, computing devices or other processing devices connected to wireless modems, as well as various forms of terminals, mobile Station (mobile station, MS), terminal (terminal) or soft terminal and so on. For example, water meters, electricity meters, sensors, etc.

2. (wireless) access network equipment (radio access network, (R)AN): used to provide network access functions for authorized user equipment in a specific area, and can use different quality transmissions according to the level of user equipment and business requirements. tunnel.

The RAN can manage radio resources, provide access services for user equipment, and then complete the forwarding of control signals and user equipment data between the user equipment and the core network. RAN can also be understood as a base station in a traditional network.

3. User plane function (UPF) network element: used for packet routing and forwarding and quality of service (QoS) processing of user plane data. User data can be connected to the data network (data network, DN) through this network element. In the embodiment of the present application, it can be used to realize the functions of the user plane network element.

4. Data network (data network, DN): used to provide a network for transmitting data. For example, a network of an operator's business, an Internet (Internet) network, a business network of a third party, and the like.

5. Authentication server function (authentication server function, AUSF) network element: mainly used for user authentication, etc.

6. Access and mobility management function (access and mobility management function, AMF) network element: mainly used for mobility management and access management, etc., and can be used to implement mobility management entity (mobility management entity, MME) functions except Functions other than session management, for example, functions such as access authorization/authentication.

7. Session management function (session management function, SMF) network element: mainly used for session management, network Internet protocol (internet protocol, IP) address allocation and management of terminal equipment, selection and management of user plane functions, policy control and charging functions The endpoint of the interface and the notification of downlink data, etc.

8. Policy control function (PCF) network element: a unified policy framework for guiding network behavior, providing policy rule information for network elements (such as AMF, SMF network elements, etc.) or terminal devices.

9. Network repository function (network repository function, NRF) network element: used to store the description information of network functional entities and the services they provide, and support service discovery, network element entity discovery and other functions.

10. Network exposure function (network exposure function, NEF) network element: used to securely expose services and capabilities provided by the 3rd Generation Partnership Project (3GPP) network function to the outside.

11. Unified data management (UDM) network element: used for unified data management, 5G user data management, processing user identification, access authentication, registration, or mobility management, etc.

12. Application function (Application function, AF) network element: It is used to route data affected by the application, access network open function network elements, and interact with the policy framework for policy control, etc.

13. Network data analysis function (network data analytics function, NWDAF) network element: NWDAF can have at least one of the following functions:

Data collection, model training, model feedback, analysis result reasoning, analysis result feedback, etc. Among them, the data collection function refers to the collection of data from network elements, third-party servers, terminal devices or network management systems; the model training function refers to the analysis and training of models based on relevant input data; the model feedback function refers to the training The machine learning model is sent to the network element that supports the reasoning function; the reasoning function of the analysis result is based on the trained machine learning model and reasoning data to make reasoning and determine the data analysis result; the feedback function of the analysis result can provide network elements, third-party servers, and terminal devices Or the network management system provides data analysis results, which can assist the network to select service quality parameters of services, or assist the network to execute traffic routing, or assist the network to select background traffic transmission strategies, etc.

Currently, the functions of the NWDAF may have the following functions: analysis logical function (analytics logical function, AnLF), model training logical function (model training logical function, MTLF), analysis logical function and model training logical function (AnLF+MTLF). The corresponding NWDAF may include the following types: NWDAF supporting reasoning, NWDAF supporting model training, and NWDAF supporting model training and reasoning.

Typical application scenarios of NWDAF include: customization or optimization of terminal parameters. That is, NWDAF collects information such as user connection management, mobility management, session management, and access services, and uses reliable analysis and prediction models to evaluate and analyze different types of users, build user portraits, and determine user movement trajectories and service usage. Habits, optimization of user mobility management parameters and radio resource management parameters, etc.; service (path) optimization, that is, NWDAF collects information such as network performance, specific area service load, user service experience, etc., and uses reliable network performance analysis and prediction models, Evaluate and analyze different types of services, construct service portraits, and determine internal correlations such as service quality of experience (QoE), service experience, service paths, or 5G service quality (quality of service, QoS) parameters , optimize business path, business routing, 5G edge computing, business corresponding to 5G QoS, etc.; AF optimizes business parameters, for example, Internet of Vehicles is an important technology of 5G network. Prediction of network performance (such as QoS information, business load) of base stations can improve the service quality of the Internet of Vehicles. For example, the Internet of Vehicles server can judge whether to continue to maintain the unmanned driving mode based on the prediction information of network performance. NWDAF collects information such as network performance and business load in a specific area, and uses reliable network performance analysis and prediction models to realize statistics and prediction of network performance and assist AF in optimizing parameters.

In the embodiment of the present application, the NWDAF may be an independent network element, or it may be set up together with other network elements. For example, the NWDAF network element can be co-configured with the AMF or with the SMF.

In addition, the above network architecture may also include a network slice selection function (NSSF), which is used to manage information related to network slices; a service communication proxy (SCP), which is used to support indirect communication, namely Support message transfer and routing between service invoking network elements and service providing network elements, selection and discovery of service providing network elements, etc. It should be understood that the network elements included in the communication system listed above are only illustrative, and the present application is not limited thereto.

In the above network architecture, the N2 interface is the interface between the RAN and the AMF network element, which is used for sending wireless parameters and non-access stratum (non-access stratum, NAS) signaling, etc.; the N3 interface is the RAN and UPF network element The interface between them is used to transmit user plane data, etc.; the N4 interface is the interface between the SMF network element and the UPF network element, and is used to transmit such as service policy, tunnel identification information of N3 connection, data cache indication information, and downlink Data notification messages and other information. The N6 interface is an interface between the DN network element and the UPF network element, and is used to transmit user plane data and the like.

It should be understood that, in the foregoing network architecture, network elements may exchange information through service interfaces. For example, the NWDAF network element can collect the data generated by the terminal on the network element through the service interface (such as Namf, Nsmf, etc.) provided by other network elements (such as AMF, SMF, etc.) (such as AMF, PCF, etc.) provide data analysis results (Analytics), models, also known as machine learning models (machine learning model), data (data), etc.

It should be understood that the above-mentioned network architecture applied to the embodiment of the present application is only an example of a network architecture described from the perspective of a traditional point-to-point architecture and a service-oriented architecture, and the network architecture applicable to the embodiment of the present application is not limited thereto. Any network architecture capable of implementing the functions of the foregoing network elements is applicable to this embodiment of the present application.

It should be noted that the names of each network element and interface in this application are just examples, and this application does not rule out the situation that each network element has another name and the functions of each network element are merged in the future. With the evolution of technology, any device or network element capable of realizing the functions of the above network elements falls within the scope of protection of the present application. Secondly, the foregoing network elements may also be referred to as entities, devices, devices or modules, etc., which are not particularly limited in this application. Moreover, in this application, for the convenience of understanding and explanation, the description of "network element" is omitted in some descriptions. For example, the NWDAF network element is referred to as NWDAF. In this case, the "NWDAF" should be understood as the NWDAF network element , hereinafter, descriptions of the same or similar situations are omitted.

In addition, in this application, the service provides network elements for data storage. For example, the service providing network element may be an NRF network element, may also be a model management (model management) network element, or may be a model management module. The model management module may be an independent network element, or a module in an NRF network element or other network elements.

For convenience of description, in the embodiments of the present application, the service providing network element is an NRF network element, and the service requesting network element and data analysis network element are NWDAF network elements as an example for description.

NWDAF(MTLF) and NWDAF(AnLF) may be deployed by different vendors, and the model running platforms used may also be different. When the vendors are different and the model running platforms are the same, the NWDAF (AnLF) of vendor B can normally receive and deploy the AI model provided by the NWDAF (MTLF) of vendor A; when the vendors are different and the model running platforms are different, the NWDAF (AnLF) of vendor B ( AnLF) cannot deploy the AI model provided by Vendor A's NWDAF (MTLF).

FIG. 2 shows a method 200 proposed by the present application, which includes:

S201. The NRF acquires feature information of the NWDAF.

The feature information includes at least one of the model running platform type supported by NWDAF and the model interoperability standard supported by NWDAF.

Wherein, the model running platform type supported by NWDAF may also be referred to as an artificial intelligence (AI) platform supported by NWDAF. The AI platforms supported by NWDAF include but are not limited to one or more of the Mindspore platform, Tensorflow platform, and PyTorch platform.

Exemplarily, the model interoperability standards supported by NWDAF include but not limited to open neural network exchange (open neural network exchange, ONNX) standard and/or predictive model markup language (predictive model markup language, PMML) standard.

For example: if both AI platform #1 and AI platform #2 support the ONNX standard, the model trained on AI platform #1 can be converted into a corresponding calculation graph, and AI platform #2 can use the calculation graph to deploy the ONNX model and perform model reasoning.

Exemplarily, the feature information of the NWDAF also includes the type of the NWDAF, the type of analysis supported by the NWDAF, the identifier of the NWDAF manufacturer, and the identifier of the service area of the NWDAF.

The following describes how NRF obtains the feature information of NWDAF:

Exemplarily, the NRF receives a plurality of registration request (for example, Nnrf_NFManagement_NFRegister Request) messages from a plurality of NWDAFs, and a plurality of NWDAFs correspond to a plurality of registration request messages one by one, and each registration request message of the plurality of registration request messages includes a corresponding The characteristic information of the NWDAF.

For example, NWDAF#1 sends a registration request message #1 to the NRF, and the registration request message #1 includes feature information #1. Correspondingly, the NRF receives the registration request message #1, and stores the feature information #1. Optionally, the NRF sends a registration response (for example, Nnrf_NFManagement_NFRegister Response) message #1 to NWDAF #1, and the registration response message #1 indicates that the feature information #1 of NWDAF #1 is stored successfully. It should be understood that NWDAF#1 is any one of the above multiple NWDAFs.

The registration request message #1 may include the following parameters:

NWDAF type (NWDAF type) parameter: identifies the type of NWDAF#1.

Analysis ID (analytics ID) parameter: identifies the type of analysis supported by NWDAF#1. For example, the analysis types supported by the NWDAF may include but not limited to one or more of service experience data analysis and network element load data analysis.

Area (area) parameter: identifies the service area of NWDAF#1. For example, the service area of NWDAF#1 may be tracking area (tracking area, TA) #1, public land mobile network (public land mobile network, PLMN) #1.

Vendor ID (vendor ID) parameter: identifies the vendor of NWDAF#1.

Supported AI platforms (supported AI platforms) parameter: identifies the AI platforms supported by NWDAF#1.

Supported model interoperability standards (supported model interoperability standards) parameter: identifies the model interoperability standards supported by NWDAF#1.

S202, NWDAF #A sends a request message #A (for example, Nnrf_NFDiscovery_Request) to NRF. Accordingly, the NRF receives the request message #A.

Request message #A is used to discover the target NWDAF. The request message #A includes the model running platform type required by NWDAF#A and/or the model interoperability standard required by NWDAF#A.

For example, the types of model running platforms supported by NWDAF#A are platform #1, platform #2 and platform #3, and the model interoperability standards supported by NWDAF are standard #1 and standard #2. In request message #A, the model running platform type required by NWDAF#A is platform #1, and the model interoperability standard required by NWDAF#A is standard #1.

Exemplarily, the request message #A also includes the target analysis type.

For example, the analysis types supported by NWDAF#A are analysis type #1, analysis type #2 and analysis type #3. The target analysis type is analysis type #1 therein.

Exemplarily, the request message #A also includes one or more of the following:

The manufacturer ID of NWDAF#A, the type of NWDAF#A, and the ID of the service area of NWDAF#A.

This application does not limit the type of NWDAF#A. The NWDAF#A may be an NWDAF supporting reasoning, an NWDAF supporting model training, or an NWDAF supporting model training and reasoning.

If NWDAF#A is an NWDAF with a model training function, there is a situation that NWDAF#A can obtain a part of the model (for example, model #A and model #B) through training, but cannot obtain another part of the model through training (for example, Model #C). In this case, in order to acquire model #C, NWDAF #A may send request message #A to NRF.

In addition, the NWDAF#A may be one of the above-mentioned multiple NWDAFs, or may not belong to the above-mentioned multiple NWDAFs, which is not limited.

S203, the NRF determines the target NWDAF according to the request message #A and the feature information of the NWDAF acquired in S201.

Exemplarily, the model execution platform type supported by the target NWDAF includes the model execution platform type required by NWDAF#A, and the model interoperability standard supported by the target NWDAF does not include the model interoperability standard required by NWDAF#A. Or, the model running platform type supported by the target NWDAF does not include the model running platform type required by NWDAF#A, and the model interoperability standard supported by the target NWDAF includes the model interoperability standard required by NWDAF#A. Alternatively, the model running platform type supported by the target NWDAF includes the model running platform type required by NWDAF#A, and the model interoperability standard supported by the target NWDAF includes the model interoperability standard required by NWDAF#A.

It should be understood that the target NWDAF may be an NWDAF supporting model training, or an NWDAF supporting model training and reasoning, without limitation.

Here are a few examples to introduce the way NRF determines the target NWDAF:

example 1:

The NRF determines the target NWDAF according to the priority of the model running platform type and model interoperability standard.

For example, if the priority of the model running platform type is higher than that of the model interoperability standard, NRF will first find the target NWDAF that supports the same model running platform as NWDAF#A from multiple NWDAFs; NWDAF#A supports the target NWDAF of the same model running platform, and NRF can find the target NWDAF that supports the same model interoperability standard as NWDAF#A from multiple NWDAFs. If there is no target NWDAF supporting the same model interoperability standard as NWDAF#A among multiple NWDAFs, the discovery process fails.

Example 2:

It is assumed that the model running platforms supported by NWDAF of the same manufacturer are the same or partially the same. The NRF determines the target NWDAF according to the priority of the vendor, model running platform type and model interoperability standard.

For example, the priority of the three is vendor, model running platform type, and model interoperability standard in order from high to low, then NRF can preferentially discover the target NWDAF of the same vendor as NWDAF#A from multiple NWDAFs; if multiple NWDAFs There is no target NWDAF from the same manufacturer as NWDAF#A, and NRF can find the target NWDAF that supports the same model running platform as NWDAF#A from multiple NWDAFs; if there is no target NWDAF that supports the same model running as NWDAF#A in multiple NWDAFs For the target NWDAF of the platform, NRF can find the target NWDAF that supports the same model interoperability standard as NWDAF#A from multiple NWDAFs; if there is no target NWDAF that supports the same model interoperability standard as NWDAF#A among the multiple NWDAFs, The discovery process failed.

Exemplarily, the NRF may not discover the target NWDAF according to the above priority order.

It should be understood that the NRF is to discover the target NWDAF among the above multiple NWDAFs.

S204. The NRF sends the address information and/or identification information of the target NWDAF to NWDAF#A. Correspondingly, NWDAF#A receives the address information and/or identification information of the target NWDAF from the NRF.

Exemplarily, the NRF may send a response message #A (for example, Nnrf_NFDiscovery_Request Response) to NWDAF #A, where the response message #A includes address information and/or identification information of the target NWDAF.

Exemplarily, the response message #A also includes the model running platform type supported by the target NWDAF and/or the model interoperability standard supported by the target NWDAF.

Exemplarily, the response message #A also includes the vendor identifier of the target NWDAF.

In addition, if the target NWDAF is not found successfully in S203, the NRF may send a response message #B to NWDAF #A, and the response message #B indicates that the discovery fails. Accordingly, NWDAF #A receives response message #B.

Or, if the target NWDAF is not found successfully in S203, the NRF may not send the response message #B to the NWDAF #A. It should be understood that if NWDAF#A does not receive a response message to the request message #A, the request may fail by default. For example, after sending the request message #A, NWDAF#A does not receive a response message for the request message #A after a preset period of time, then NWDAF#A determines that the request fails.

S205, NWDAF #A sends a request message #B to the target NWDAF according to the address information and/or identification information of the target NWDAF (for example, the request message #B is a model request message, such as Nnwdaf_MLModelInfo Request). Accordingly, the target NWDAF receives the request message #B.

The request message #B includes the target analysis type. The request message #B is used to request the model corresponding to the target analysis type.

Exemplarily, if the model execution platform type supported by the target NWDAF does not include the model execution platform type required by NWDAF#A, and the model interoperability standard supported by the target NWDAF includes the model interoperability standard required by NWDAF#A, then the request message #B Includes model interoperability standards required by NWDAF#A.

It should be understood that including the model interoperability standard required by NWDAF #A in the request message #B is to allow the target NWDAF to provide a model conforming to the model interoperability standard required by NWDAF #A.

S206. The target NWDAF sends the model corresponding to the target analysis type, or the address of the model corresponding to the target analysis type, to NWDAF#A. Correspondingly, NWDAF#A receives the model corresponding to the target analysis type from the target NWDAF, or the address of the model corresponding to the target analysis type.

Exemplarily, the target NWDAF may send a response message #C (eg, Nnwdaf_MLModelInfo Response) to NWDAF #A. The response message #C includes the model corresponding to the target analysis type, or the address of the model corresponding to the target analysis type.

According to the method of the present application, the NRF determines the target NWDAF according to the feature information of the NWDAF and the request message of NWDAF#A. The target NWDAF may belong to different manufacturers from NWDAF#A, so that the AI model can be distributed across manufacturers, breaking the limitation that the AI model can only be shared with the manufacturer, and improving the flexibility of AI model distribution.

In method 200, the target NWDAF is determined by the NRF. As another way, the target NWDAF may be determined by NWDAF#A, see method 300 below for details.

FIG. 3 shows a method 300 proposed by the present application, which includes:

S301. The NRF acquires feature information of the NWDAF.

The feature information of NWDAF includes the analysis types supported by NWDAF.

Exemplarily, the feature information of the NWDAF also includes the model running platform supported by the NWDAF and/or the model interoperability standard supported by the NWDAF, as well as the type of the NWDAF, the NWDAF manufacturer's identifier, and the NWDAF's service area identifier.

The NRF can obtain feature information of multiple NWDAFs, and for this process, refer to the description of S201.

S302, NWDAF #A sends a request message #a (for example, Nnrf_NFDiscovery_Request) to NRF. Accordingly, the NRF receives the request message #a.

The request message #a includes the target analysis type, and the request message #a is used to request to discover candidate NWDAFs. Analysis types supported by candidate NWDAFs include target analysis types.

S303, the NRF determines a candidate NWDAF according to the request message #a and the feature information of the NWDAF acquired in S301.

It should be understood that NRF is the discovery of candidate NWDAFs among the plurality of NWDAFs above.

The difference between S303 and S203 is introduced below:

In S303, the NRF determines a candidate NWDAF, and the candidate NWDAF only needs to be able to provide a model corresponding to the target analysis type. NRF does not care whether the candidate NWDAF supports the same model running platform or the same model interoperability standard as NWDAF#A.

It should be understood that the candidate NWDAF may include at least one NWDAF, and any one of the at least one NWDAF may be an NWDAF supporting model training or an NWDAF supporting reasoning and model training.

Additionally, if the NRF finds no eligible candidate NWDAFs, the discovery process fails.

S304. The NRF sends at least one of the model running platform type supported by the candidate NWDAF and the model interoperability standard supported by the candidate NWDAF, and address information and/or identification information of the candidate NWDAF to NWDAF#A.

Exemplarily, the NRF may send a response message #a (for example, Nnrf_NFDiscovery_Request Response) to NWDAF #A, and the response message #a includes at least one of the model running platform type supported by the candidate NWDAF and the model interoperability standard supported by the candidate NWDAF, And the address information and/or identification information of the candidate NWDAF.

Exemplarily, the response message #a may also include the vendor identifier of the candidate NWDAF and the service area identifier of the candidate NWDAF.

In addition, if the candidate NWDAF is not found successfully in S303, the NRF sends a response message #b to NWDAF #A, and the response message #b indicates that the discovery fails.

Or, if the candidate NWDAF is not found successfully in S303, the NRF may not send the response message #b to NWDAF #A. It should be understood that if NWDAF#A does not receive a response message to the request message #a, the request may fail by default.

S305, NWDAF#A determines the target NWDAF according to the model running platform type supported by the candidate NWDAF and/or the model interoperability standard supported by the candidate NWDAF.

It should be understood that NWDAF#A is to find the target NWDAF among the candidate NWDAFs.

Exemplarily, the model execution platform type supported by the target NWDAF includes the model execution platform type required by NWDAF#A, and the model interoperability standard supported by the target NWDAF does not include the model interoperability standard required by NWDAF#A.

Exemplarily, the model running platform type supported by the target NWDAF does not include the model running platform type required by NWDAF#A, and the model interoperability standard supported by the target NWDAF includes the model interoperability standard required by NWDAF#A.

Exemplarily, the model running platform type supported by the target NWDAF includes the model running platform type required by NWDAF#A, and the model interoperability standard supported by the target NWDAF includes the model interoperability standard required by NWDAF#A.

For the manner in which NWDAF#A determines the target NWDAF, reference may be made to Example 1 and Example 2 in S203. That is, NWDAF#A executes the operations of the NRF in the first and second examples of S203.

For example, NWDAF#A can determine the target NWDAF according to the model runtime platform type and the priority of the model interoperability standard. For another example, NWDAF#A determines the target NWDAF according to the priority of the vendor, model running platform type and model interoperability standard. I won't repeat them here.

S306, NWDAF #A sends a request message #b to the target NWDAF (for example, request message #b is a model request message, such as Nnwdaf_MLModelInfo Request). Accordingly, the target NWDAF receives the request message #b.

The request message #b includes the target analysis type, and the request message #b is used to request a model corresponding to the target analysis type.

For this process, reference may be made to the description of S205, which will not be repeated here.

S307. The target NWDAF sends the model corresponding to the target analysis type, or the address of the model corresponding to the target analysis type, to NWDAF#A. Correspondingly, NWDAF#A receives the model corresponding to the target analysis type from the target NWDAF, or the address of the model corresponding to the target analysis type.

According to the method of the present application, NWDAF#A can determine the target NWDAF according to the characteristic information of the candidate NWDAF. The target NWDAF may belong to different manufacturers from NWDAF#A, so that the AI model can be distributed across manufacturers, breaking the limitation that the AI model can only be shared with the manufacturer, and improving the flexibility of AI model distribution.

According to the foregoing method, FIG. 4 is a communication device provided in an embodiment of the present application, and the communication device includes a transceiver unit 401 and a processing unit 402 .

Wherein, the transceiving unit 401 may be used to implement corresponding information transceiving functions. The transceiver unit 401 may also be called a communication interface or a communication unit. The processing unit 402 may be configured to perform processing operations.

Exemplarily, the device further includes a storage unit, which can be used to store instructions and/or data, and the processing unit 402 can read the instructions and/or data in the storage unit, so that the device implements the above-mentioned method embodiments. action of the device.

As a first implementation manner, the device may be the NRF network element in the foregoing embodiments, or may be a component (such as a chip) of the NRF network element. Wherein, the transceiver unit and the processing unit may be used to implement related operations of the NRF network element in each method embodiment above.

As a second implementation manner, the device may be the NWDAF#A network element in the foregoing embodiments, or may be a component (such as a chip) of the NWDAF#A network element. Wherein, the transceiver unit and the processing unit can be used to implement the related operations of the NWDAF#A network element in each method embodiment above.

As a third implementation manner, the device may be the target NWDAF network element in the foregoing embodiments, or may be a component (such as a chip) of the target NWDAF network element. Wherein, the transceiver unit and the processing unit may be used to implement related operations of the target NWDAF network element in each method embodiment above.

It should be understood that the specific process of each unit performing the above corresponding steps has been described in detail in the above method embodiments, and for the sake of brevity, details are not repeated here.

It should also be understood that the means herein are embodied in the form of functional units. The term "unit" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor for executing one or more software or firmware programs (such as a shared processor, a dedicated processor, or a group processor, etc.) and memory, incorporated logic, and/or other suitable components to support the described functionality. In an optional example, those skilled in the art can understand that the device may specifically be the first network element in the above-mentioned embodiments, and may be used to execute each process corresponding to the first network element in the above-mentioned method embodiments and/or steps, or, the device may specifically be the network management network element in the above embodiments, and may be used to execute the various processes and/or steps corresponding to the network management network elements in the above method embodiments. In order to avoid repetition, it is not repeated here repeat.

The above-mentioned communication device has the function of implementing the corresponding steps performed by the device in the above-mentioned method. The functions may be implemented by hardware, or may be implemented by executing corresponding software through hardware. The hardware or software includes one or more modules corresponding to the above-mentioned functions; for example, the transceiver unit can be replaced by a transceiver (for example, the sending unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver ), and other units, such as a processing unit, can be replaced by a processor to respectively perform the sending and receiving operations and related processing operations in each method embodiment.

In addition, the above-mentioned transceiver unit 401 may also be a transceiver circuit (for example, may include a receiving circuit and a sending circuit), and the processing unit may be a processing circuit.

It should be noted that the device in FIG. 4 may be the device in the foregoing method embodiment, or may be a chip or a chip system, for example: a system on chip (system on chip, SoC). Wherein, the transceiver unit may be an input-output circuit or a communication interface; the processing unit is a processor or a microprocessor or an integrated circuit integrated on the chip. It is not limited here.

The embodiment of the present application also provides a communication device, as shown in FIG. 5 , including: a processor 501 and a communication interface 502 . The processor 501 is configured to execute computer programs or instructions stored in the memory 503, or read data stored in the memory 503, so as to execute the methods in the above method embodiments. Exemplarily, there are one or more processors 501 . The communication interface 502 is used for receiving and/or sending signals. For example, the processor 501 is configured to control the communication interface 502 to receive and/or send signals.

Exemplarily, as shown in FIG. 5 , the communication device further includes a memory 503 for storing computer programs or instructions and/or data. The memory 503 can be integrated with the processor 501, or can also be set separately. Exemplarily, there are one or more memories 503 .

Exemplarily, the processor 501, the communication interface 502, and the memory 503 are interconnected via a bus 504; the bus 504 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA ) bus, etc. The above-mentioned bus 504 can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is used in FIG. 5 , but it does not mean that there is only one bus or one type of bus.

For example, the processor 501 is configured to execute the computer programs or instructions stored in the memory 503, so as to implement related operations of the NRF network element, the NWDAF#A network element, or the target NWDAF network element in each method embodiment above.

It should be understood that the processor (such as the processor 501) mentioned in the embodiment of the present application may be a central processing unit (central processing unit, CPU), a network processor (network processor, NP) or a combination of CPU and NP. The processor may further include hardware chips. The aforementioned hardware chip may be an application-specific integrated circuit (application-specific integrated circuit, ASIC), a programmable logic device (programmable logic device, PLD) or a combination thereof. The aforementioned PLD may be a complex programmable logic device (complex programmable logic device, CPLD), a field-programmable gate array (field-programmable gate array, FPGA), a general array logic (generic array logic, GAL) or any combination thereof.

It should also be understood that the memory (such as the memory 503 ) mentioned in the embodiments of the present application may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the non-volatile memory can be read-only memory (read-only memory, ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically programmable Erases programmable read-only memory (electrically EPROM, EEPROM) or flash memory. Volatile memory can be random access memory (RAM), which acts as external cache memory.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated. to another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

A unit described as a separate component may or may not be physically separated, and a component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Parts or units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute some or part of the steps of the method in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

The above is only the specific implementation of the application, but the scope of protection of the application is not limited thereto. Anyone familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the application, and should cover Within the protection scope of this application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

A communication method, characterized in that, comprising:

The service providing network element acquires feature information of the data analysis network element, where the feature information includes at least one of a model running platform type supported by the data analysis network element and a model interoperability standard supported by the data analysis network element;

The service providing network element receives a request message from the service requesting network element, the request message is used to request to discover the target data analysis network element, and the request message includes the type of model running platform required by the service requesting network element and/or The model interoperability standard required by the service requesting network element;

The service providing network element determines the target data analysis network element according to the characteristic information and the request message, and the data analysis network element includes the target data analysis network element;

The service providing network element sends the address information and/or identification information of the target data analysis network element to the service requesting network element.
The method according to claim 1, characterized in that,

The model running platform type supported by the target data analysis network element includes the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element does not include the model running platform type required by the service requesting network element. Model Interoperability Standard; or,

The model running platform type supported by the target data analysis network element does not include the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element includes the model running platform type required by the service requesting network element Model Interoperability Standard; or,

The model running platform type supported by the target data analysis network element includes the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element includes the model required by the service requesting network element interoperability standards.
The method according to claim 1 or 2, characterized in that,

The service providing network element determines the target data analysis network element according to the characteristic information and the request message, including:

The service providing network element determines the target data analysis network element according to the model running platform type and the priority of the model interoperability standard.
The method according to claim 3, characterized in that,

Model runtime platform types take precedence over model interoperability standards.
The method according to any one of claims 1-4, wherein the method further comprises:

The service providing network element sends the model running platform type supported by the target data analysis network element and/or the model interoperability standard supported by the target data analysis network element to the service requesting network element.
The method according to any one of claims 1-5, characterized in that,

The characteristic information also includes at least one of the type of the data analysis network element, the analysis type supported by the data analysis network element, the manufacturer identification of the data analysis network element, and the service area identification of the data analysis network element .
The method according to any one of claims 1-6, characterized in that,

The service providing network element is a network storage function network element;

The target data analysis network element is a network data analysis function network element supporting model training, or a network data analysis function network element supporting reasoning and model training;

The service requesting network element is a network data analysis function network element supporting reasoning.
A communication method, characterized in that, comprising:

The service requesting network element sends a request message to the service providing network element, the request message is used to request to find the target data analysis network element, and the request message includes the type of the model running platform required by the service requesting network element and/or the service Request model interoperability standards required by network elements;

The service requesting network element receives address information and/or identification information of the target data analyzing network element from the service providing network element;

The service requesting network element sends a model request message to the target data analysis network element according to the address information and/or the identification information, the model request message includes the target analysis type, and the model request message is used to request the The model corresponding to the target analysis type;

The service requesting network element receives the model corresponding to the target analysis type from the target data analysis network element, or the address of the model corresponding to the target analysis type.
The method according to claim 8, characterized in that,

The model running platform type supported by the target data analysis network element includes the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element does not include the model running platform type required by the service requesting network element. Model Interoperability Standard; or,

The model running platform type supported by the target data analysis network element does not include the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element includes the model running platform type required by the service requesting network element Model Interoperability Standard; or,

The model running platform type supported by the target data analysis network element includes the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element includes the model required by the service requesting network element interoperability standards.
The method according to claim 8 or 9, wherein the method further comprises:

The service requesting network element receives the model running platform type supported by the target data analysis network element and/or the model interoperability standard supported by the target data analysis network element from the service providing network element;

The model running platform type supported by the target data analysis network element does not include the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element includes the model running platform type required by the service requesting network element. Model interoperability standards, the model request message includes the model interoperability standards required by the service requesting network element.
The method according to any one of claims 8-10, characterized in that,

The service providing network element is a network storage function network element;

The service request network element is a network data analysis function network element supporting reasoning;

The target data analysis network element is a network element with a network data analysis function supporting model training, or a network element with a network data analysis function supporting reasoning and model training.
A communication method, characterized in that, comprising:

The service providing network element acquires feature information of the first data analysis network element, where the feature information includes analysis types supported by the first data analysis network element;

The service providing network element receives a request message from a service requesting network element, the request message is used to request to discover a second data analysis network element, the request message includes a target analysis type, and the second data analysis network element supports The analysis type includes the target analysis type; the first data analysis network element includes the second data analysis network element;

The service providing network element determines the second data analysis network element according to the characteristic information and the request message;

The service providing network element sends at least one of the model running platform type supported by the second data analysis network element and the model interoperability standard supported by the second data analysis network element to the service requesting network element, and the The address information and/or identification information of the second data analysis network element.
The method according to claim 12, characterized in that,

The feature information also includes the model running platform type supported by the first data analysis network element and/or the model interoperability standard supported by the first data analysis network element.
The method according to claim 12 or 13, characterized in that,

The feature information further includes at least one of the type of the first data analysis network element, a manufacturer identifier of the first data analysis network element, and a service area identifier of the first data analysis network element.
The method according to any one of claims 12-14, characterized in that,

The service providing network element is a network storage function network element;

The service request network element is a network data analysis function network element supporting reasoning;

The second data analysis network element includes a network data analysis function network element supporting model training, and/or a network data analysis function network element supporting reasoning and model training.
A communication method, characterized in that, comprising:

The service requesting network element sends a request message to the service providing network element, the request message is used to request to find a candidate data analysis network element, the request message includes a target analysis type, and the analysis types supported by the candidate data analysis network element include the target analysis type;

The service requesting network element receives feature information of the candidate data analysis network element from the service providing network element, and the feature information includes the model running platform type supported by the candidate data analysis network element and the candidate data analysis network element. At least one of the model interoperability standards supported by the network element;

The service requesting network element determines a target data analysis network element according to the feature information, and the candidate data analysis network element includes the target data analysis network element;

The service requesting network element sends a model request message to the target data analysis network element, and the model request message is used to request a model corresponding to the target analysis type;

The service requesting network element receives the model corresponding to the target analysis type or the address of the model corresponding to the target analysis type from the target data analysis network element.
The method according to claim 16, characterized in that,

The model running platform type supported by the target data analysis network element includes the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element does not include the model running platform type required by the service requesting network element. Model Interoperability Standard; or,

The model running platform type supported by the target data analysis network element does not include the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element includes the model running platform type required by the service requesting network element Model Interoperability Standard; or,

The model running platform type supported by the target data analysis network element includes the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element includes the model required by the service requesting network element interoperability standards.
The method according to claim 16 or 17, characterized in that,

The service requesting network element determining the target data analysis network element according to the feature information includes:

The service requesting network element determines the target data analysis network element according to the model running platform type and the priority of the model interoperability standard.
The method of claim 18, wherein,

Model runtime platform types take precedence over model interoperability standards.
The method according to any one of claims 16-19, wherein,

The model running platform type supported by the target data analysis network element does not include the model running platform type required by the service requesting network element, and the model interoperability standard supported by the target data analysis network element includes the model running platform type required by the service requesting network element. Model interoperability standards, the model request message includes the model interoperability standards required by the service requesting network element.
The method according to any one of claims 16-20, characterized in that,

The service providing network element is a network storage function network element;

The service request network element is a network data analysis function network element supporting reasoning;

The candidate data analysis network element includes a network data analysis function network element that supports model training, and/or, a network data analysis function network element that supports reasoning and model training;

The target data analysis network element is a network element with a network data analysis function supporting model training, or a network element with a network data analysis function supporting reasoning and model training.
A communication device, characterized by comprising:

memory for storing computer instructions;

A processor, configured to execute the computer instructions, so that the communication device executes the method according to any one of claims 1-21.
A computer-readable storage medium, characterized in that it includes a computer program or an instruction, and when the computer program or the instruction is run on a computer, the computer executes the computer program described in any one of claims 1-21. Methods.
A computer program product, characterized by comprising instructions, which, when run on a computer, cause the computer to execute the method according to any one of claims 1-21.
A communication system, characterized by comprising: a service providing network element and a service requesting network element;

The service network element is used to perform the method according to any one of claims 1-7, and the service requesting network element is used to perform the method according to any one of claims 8-11; or,

The service network element is configured to execute the method according to any one of claims 12-15, and the service requesting network element is configured to execute the method according to any one of claims 16-21.